List your company

Physics Reasoning on MMLU-Pro Physics

88.5AccuracySC
40.1452.69565.2577.805Jul 8, 2026

Evaluation results

MethodLinks
SCBackbone=Qwen3-30B-Instruct, Inference Strategy=SC2026.0788.5
MILESBackbone=Qwen3-30B-Instruct, Inference Strategy=MILES2026.0788.5
MILESBackbone=GPT-OSS-20B, Inference Strategy=MILES2026.0787
ZS-CoTBackbone=Qwen3-30B-Instruct, Inference Strategy=ZS-CoT2026.0787
SCBackbone=GPT-OSS-20B, Inference Strategy=SC2026.0786.5
BoTBackbone=Qwen3-30B-Instruct, Inference Strategy=BoT2026.0786
ZS-CoTBackbone=GPT-OSS-20B, Inference Strategy=ZS-CoT2026.0785.5
MILESBackbone=GPT-4.1-mini, Inference Strategy=MILES2026.0785
MILESBackbone=GPT-4.1, Inference Strategy=MILES2026.0784.5
BoTBackbone=GPT-4.1, Inference Strategy=BoT2026.0784
SCBackbone=GPT-4.1-mini, Inference Strategy=SC2026.0783.5
DCBackbone=GPT-4.1-mini, Inference Strategy=DC2026.0783.5
BoTBackbone=GPT-4.1-mini, Inference Strategy=BoT2026.0783
SCBackbone=GPT-4.1, Inference Strategy=SC2026.0783
ZS-CoTBackbone=GPT-4.1-mini, Inference Strategy=ZS-CoT2026.0782
ZS-CoTBackbone=GPT-4.1, Inference Strategy=ZS-CoT2026.0781
DCBackbone=GPT-OSS-20B, Inference Strategy=DC2026.0779
DCBackbone=GPT-4.1, Inference Strategy=DC2026.0778
DCBackbone=Qwen3-30B-Instruct, Inference Strategy=DC2026.0763.5
BoTBackbone=GPT-OSS-20B, Inference Strategy=BoT2026.0742